© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6967
    Prev
    Next
    INDEX
    Explanations

    Starts with a or ar

    np_acts-logits-general · gemini-2.5-flash-lite

    algorithm, arithmetic, atmospheric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    د
    0.94
    كان
    0.94
    д
    0.88
    بر
    0.77
     canciones
    0.75
    ι
    0.70
    دە
    0.70
     ausgewählt
    0.69
    த
    0.69
     در
    0.68
    POSITIVE LOGITS
    2
    1.20
    0
    0.94
    ric
    0.93
    8
    0.88
    ,
    0.84
    ę
    0.84
    ну
    0.83
    ;
    0.82
    /
    0.81
    一
    0.79
    Activations Density 0.725%

    No Known Activations